In milanwiedemann/lcstools: Univariate and Bivariate Latent Change Score Modelling

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

library(lcsm)
library(lavaan)

The main underlying functions to extract parameters and fit statistics come from the broom package: broom::tidy() and broom::glance(). The functions extract_param() and extract_fit() offer some tools that I find helpful when running LCSMs in R, for example:

• extract_param(): only one row per estimated parameter,
• extract_fit(): fit statistics for multiple lavaan objects can be extracted.

Create univariate models

# First fit some latent change score models

# No change model
uni_lcsm_01 <- fit_uni_lcsm(data = data_uni_lcsm, 
                            var = c("x1", "x2", "x3", "x4", "x5"),
                            model = list(alpha_constant = FALSE, 
                                         beta = FALSE, 
                                         phi = FALSE))
# Constant change only model
uni_lcsm_02 <- fit_uni_lcsm(data = data_uni_lcsm, 
                            var = c("x1", "x2", "x3", "x4", "x5"),
                            model = list(alpha_constant = TRUE, 
                                         beta = FALSE, 
                                         phi = FALSE))

# Constant change and proportional change (Dual change model)
uni_lcsm_03 <- fit_uni_lcsm(data = data_uni_lcsm, 
                            var = c("x1", "x2", "x3", "x4", "x5"),
                            model = list(alpha_constant = TRUE, 
                                         beta = TRUE, 
                                         phi = FALSE))

Extract fit statistics

This function takes the lavaan objects as input and returns some fit statistics. More fit statistics can be returned using the argument details = TRUE.

# Extract fit statistics
fit_uni_lcsm <- extract_fit(uni_lcsm_01, uni_lcsm_02, uni_lcsm_03)

# Print table of parameter estimates
knitr::kable(fit_uni_lcsm, 
             digits = 3, 
             caption = "Parameter estimates for bivariate LCSM")

Extract parameters

# Now extract parameter estimates
param_uni_lcsm_02 <- extract_param(uni_lcsm_03, printp = TRUE)

# Print table of parameter estimates
knitr::kable(param_uni_lcsm_02, 
             digits = 3, 
             caption = "Parameter estimates for bivariate LCSM")

TODOs

• For now see example in README file on Github or shinyApp "shinychange"
• step by step example here building all the way up to a univariate lcsm
• select data
• run univariate models
• add parameters and compare results using anova and model parameters
• use grimm 2017 data?

milanwiedemann/lcstools documentation built on March 3, 2023, 5:14 a.m.